FRVT 1:N Identification For Paperless Travel
Latest Report | Algorithm Submission
Status
[2021-07-13]
We have released a new report from the Face Recognition Vendor Test (FRVT) program:
Part 7: Identification for Paperless Travel and Immigration.
As described in this
press release,
the report describes the paperless travel application,
details the kinds of biometric errors that can occur, and includes extensive results from simulations of
face recognition for boarding an aircraft and traversing an airport security point.
The report will be updated on a regular basis as new analyses are implemented,
and as results for newly submitted FRVT algorithms are produced.
Motivation
One-to-many facial recognition is being used in airport transit settings with a traveler’s face
being matched against galleries of individuals expected to be present.
This allows, for example, the traditional boarding pass to be replaced with
the presentation of a biometric - the face - to a camera. During aircraft boarding, the biometric
is serving a double role, first for access control to an aircraft and, second, for
facilitation of a visa holder recording their departure from a country.
Performance
[2021-07-13]
The table below shows the False Negative Identification Rates - “miss rates” -
as the percentage of travelers not matched to their gallery photo(s). This is
done where a threshold is set to limit the False Positive Identification Rate
(FPIR) to 0.003. In this leaderboard, the 420 person galleries represent
aircraft boarding while the 42000-person trial represents a centralized airport security line where
many more people are expected in a given temporal window. The k value represents the number of images of
each enrollee in each gallery.
Contact Information
Inquiries and comments may be submitted to frvt@nist.gov.
Subscribe
Subscribe to the FRVT mailing list to receive emails when announcements or updates are made.
Related NIST Projects